Publication number | US6430160 B1 |

Publication type | Grant |

Application number | US 09/515,927 |

Publication date | Aug 6, 2002 |

Filing date | Feb 29, 2000 |

Priority date | Feb 29, 2000 |

Fee status | Paid |

Also published as | WO2001065268A1 |

Publication number | 09515927, 515927, US 6430160 B1, US 6430160B1, US-B1-6430160, US6430160 B1, US6430160B1 |

Inventors | Donald E. Smith, Man Li |

Original Assignee | Verizon Laboratories Inc. |

Export Citation | BiBTeX, EndNote, RefMan |

Patent Citations (8), Non-Patent Citations (6), Referenced by (84), Classifications (29), Legal Events (6) | |

External Links: USPTO, USPTO Assignment, Espacenet | |

US 6430160 B1

Abstract

A method (**1000**) of estimating the delays that data packets experiences along a path in an IP network is presented. The method involves sending probe packets (**102**), transmitted along the same path as the data whose delays are to be estimated, with a frequency dictated by statistics that include Poisson statistics. Information obtained about the delays in the probe packet transmissions may be used to estimate data delays.

Claims(23)

1. A method of estimating data delays in transmitting data packets from a first location to a second location on a computer network comprising

identifying a bottleneck link in a path connecting the first location to the second location;

determining a queuing delay of probes at the bottleneck link by injecting probe packets at the first location according to departure statistics governing a probability distribution such that arrival times of the probe packets at the second location are consistent with the probability distribution; and

estimating a queuing delay of data from the queuing delay of probes at the bottleneck link.

2. A method of estimating data delays in transmitting data packets from a first location to a second location on a computer network as in claim 1 , further comprising adding a sum of data service times and a propagation delay to the queuing delay to obtain an estimate of the data delays.

3. A method of estimating data delays in transmitting data packets from a first location to a second location on a computer network as in claim 2 , wherein determining a queuing delay of probes at the bottleneck link by injecting probe packets at the first location includes subtracting a sum of probe service times and a propagation delay from first location to second location probe delays.

4. A method of estimating data delays in transmitting data packets from a first location to a second location on a computer network as in claim 2 , wherein determining a queuing delay of probes at the bottleneck link by injecting probe packets at the first location includes injecting probe packets according to a Poisson distribution.

5. A method of estimating data delays in transmitting data packets from a first location to a second location on a computer network as in claim 2 , further comprising determining a data packet length distribution served by the bottleneck link.

6. A method of estimating data delays in transmitting data packets from a first location to a second location on a computer network comprising transmitting probe packets on the computer network according to departure statistics consistent with a stochastic process such that arrival times of the probe packets at the second location are consistent with the stochastic process;

determining probe delays for said probe packets to travel from the first location to the second location;

estimating a time average from the probe delays with a prescribed accuracy; and

relating the time average to the data delays.

7. A method of estimating data delays in transmitting data packets from a first location to a second location on a computer network as in claim 6 , wherein transmitting probe packets on the computer network includes transmitting probe packets on the computer network from the first location to the second location.

8. A method of estimating data delays in transmitting data packets from a first location to a second location on a computer network as in claim 7 , wherein transmitting probe packets on the computer network from the first location to the second location includes transmitting probe packets on the computer network from the first location to the second location according to departure statistics consistent with a Poisson process.

9. A system for estimating data delays in transmitting data packets from a first location to a second location on a computer network comprising

a computer;

instructions for said computer for identifying a bottleneck link in a path connecting the first location to the second location;

instructions for said computer for determining a queuing delay of probes at the bottleneck link by injecting probe packets at the first location according to a probability distribution such that arrival times of the probe packets at the second location are consistent with the probability distribution; and

instructions for said computer for estimating a queuing delay of data from the queuing delay of probes at the bottleneck link.

10. A system for estimating data delays in transmitting data packets from a first location to a second location on a computer network as in claim 9 , further comprising instructions for said computer for adding a sum of data service times and a propagation delay to the queuing delay to obtain an estimate of the data delays.

11. A system for estimating data delays in transmitting data packets from a first location to a second location on a computer network as in claim 10 , wherein instructions for determining a queuing delay of probes at the bottleneck link by injecting probe packets at the first location includes instructions for subtracting a sum of probe service times and a propagation delay from first location to second location probe delays.

12. A system for estimating data delays in transmitting data packets from a first location to a second location on a computer network as in claim 11 , wherein the probability distribution is a Poisson distribution.

13. A system for estimating data delays in transmitting data packets from a first location to a second location on a computer network as in claim 10 , further comprising instructions for determining a data packet length distribution served by the bottleneck link.

14. A system for estimating data delays in transmitting data packets from a first location to a second location on a computer network comprising

a computer;

instructions for said computer for transmitting probe packets on the computer network according to departure statistics consistent with a stochastic process such that arrival times of the probe packets at the second location are consistent with the stochastic process;

instructions for said computer for determining probe delays for said probe packets to travel from the first location to the second location;

instructions for said computer for estimating a time average from the probe delays with a prescribed accuracy; and

instructions for said computer for relating the time average to the data delays.

15. A system for estimating data delays in transmitting data packets from a first location to a second location on a computer network according to claim 14 , wherein the stochastic process is a Poisson process.

16. A method of approximating a time average of a time-dependent variable, V, said variable representing a virtual delay of a packet upon arrival at a network link at a time t, comprising

sending N probe packets to said data link;

recording a time of arrival, A_{k}, where 1≦k≦N, of each of the N probe packets at said data link;

calculating a sum of V(A_{k}), from k=1 to k_{max}, where k_{max }and only k_{max}, of the N probe packets arrive at said data link before or at the time t;

calculating an expectation value of a number of packets to arrive at said data link;

calculating an estimator, Z(t), given by the quotient of said sum and said expectation value of a number of packets; and

approximating said time average by said estimator by bounding a variance of a difference between said estimator and said time average, said variance given by an expectation value of a time average of V(t)^{2}, divided by said expectation value of a number of packets.

17. A method of approximating a time average of a time-dependent variable V, said time average given by $\frac{1}{t}\ue89e{\int}_{0}^{t}\ue89eV\ue89e\left(s\right)\ue89e\text{\hspace{1em}}\ue89e\uf74ct,$

where V represents a virtual delay of a packet upon arrival at a network link at the time t, comprising

sending N probe packets to said data link so that a first of the N probe packets arrives at time A_{l}, a second at time A_{2}, a third at time A_{3}, . . . , and an Nth at time A_{N}, where the times A_{1}≦A_{2}≦A_{3}≦ . . . ≦A_{N }are consistent with a Poisson process of rate λ_{p; }

calculating an estimator Z(t), given by $Z\ue89e\left(t\right)=\frac{1}{{\lambda}_{p}\ue89et}\ue89e\sum _{k=1}^{{k}_{\mathrm{max}}}\ue89e\text{\hspace{1em}}\ue89eV\ue89e\left({A}_{k}\right)$

where

and

approximating said time average by Z(t) by bounding a variance of a difference between Z(t) and said time average, said variance given by an expectation value of ${t}^{-1}\ue89e{\int}_{0}^{t}\ue89e{\ue8a0V\ue89e\left(s\right)\ue8a0}^{2}\ue89e\text{\hspace{1em}}\ue89e\uf74cs\xf7\left({\lambda}_{p}\ue89et\right).$

18. For a variable I(V(t)>x) that depends on a time t and a parameter x, a method of approximating a time average of the variable I(V(t)>x), said variable I(V(t)>x) equal to unity if V(t), a virtual delay of a packet upon arrival at a network link at a time t, is greater than the parameter x, and equal to zero otherwise, comprising

sending N probe packets to said data link;

recording a time of arrival, A_{k}, where 1≦k≦N. of each of the N probe packets at said data link;

calculating a sum of I(A_{k}>x), from k=1 to k_{max}=, where k_{max}, and only k_{max}, of the N probe packets arrive at said data link before or at the time t, and I(A_{k}>x) is equal to unity if A_{k }is greater than the parameter x, and equal to zero otherwise;

calculating an expectation value of a number of packets to arrive at said data link;

calculating an estimator, Z(t), given by the quotient of said sum and said expectation value of a number of packets; and

approximating said time average by said estimator by bounding a variance of a difference between said estimator and said time average, said variance given by an expectation value of a time average of I(V(t)>x)^{2 }divided by said expectation value of a number of packets.

19. A method of approximating a time average of a variable I(V(t)>x) that depends on a time t and a parameter x, said time average given by $\frac{1}{t}\ue89e{\int}_{0}^{t}\ue89eI\ue89e\left(V\ue89e\left(t\right)>x\right)\ue89e\text{\hspace{1em}}\ue89e\uf74ct,$

where the variable I(V(t)>x) is equal to unity if V(t), a virtual delay of a packet upon arrival at a network link at a time t, is greater than x, and equal to zero otherwise, comprising

sending N probe packets to said data link so that a first of the N probe packets arrives at time A_{1}, a second at time A_{2}, a third at time A_{3}, . . . , and an Nth at time A_{N}, where the times A_{1}≦A_{2}≦A_{3}≦ . . . ≦A_{N}are consistent with a Poisson process of rate λ_{p};

calculating an estimator Z(t), given by $Z\ue89e\left(t\right)=\frac{1}{{\lambda}_{p}\ue89et}\ue89e\sum _{k=1}^{{k}_{\mathrm{max}}}\ue89e\text{\hspace{1em}}\ue89eI\ue89e\left({A}_{k}>x\right)$

where k_{max}=max{k|A_{k}>t}, and I(A_{k}>x) is equal to unity if A_{k }is greater than the parameter x, and equal to zero otherwise; and

approximating said time average by Z(t) by bounding a variance of a difference between Z(t) and said time average, said variance given by an expectation value of ${t}^{-1}\ue89e{\int}_{0}^{t}\ue89e{\ue8a0I\ue89e\left(V\ue89e\left(s\right)>x\right)\ue8a0}^{2}\ue89e\text{\hspace{1em}}\ue89e\uf74cs\xf7\left({\lambda}_{p}\ue89et\right).$

20. A method of approximating an expectation value, E(W^{d}), of a delay experienced by a data packet arriving at a network link, comprising

computing a time average of a time-dependent variable, V(t), said variable representing a virtual delay of a packet upon arrival at the network link at a time t, where said time average is given by $\frac{1}{t}\ue89e{\int}_{0}^{t}\ue89eV\ue89e\left(s\right)\ue89e\text{\hspace{1em}}\ue89e\uf74cs;$

computing an expectation value, E(U), of a packet size;

computing an expectation value, E(U^{2}), of a square of the packet size,

utilizing said time average, said expectation value of a packet size, said expectation value of a square of the packet size, and a server utilization, ρ, to approximate said expectation value of a delay.

21. A method of approximating an expectation value, E(W^{d}) of a delay experienced by a data packet arriving at a network link as in claim 20 , wherein utilizing said time average, said expectation value of a packet size, said expectation value of a square of the packet size, and a server utilization, ρ, includes utilizing said time average, said expectation value of a packet size, said expectation value of a square of the packet size, and a server utilization, ρ, to approximate said expectation value of a delay according to $E\ue8a0\left({W}^{d}\right)\approx \frac{1}{\rho}\ue89e\frac{1}{t}\ue89e{\int}_{0}^{t}\ue89eV\ue89e\left(s\right)\ue89e\text{\hspace{1em}}\ue89e\uf74cs-\frac{E\ue89e\left({U}^{2}\right)}{2\ue89eE\ue89e\left(U\right)}.$

22. A method of approximating an expectation value, E(I(W^{d}>x)), of a variable I(W^{d}>x) that depends on a parameter x, said variable I(W^{d}>x) equal to unity if a delay of a data packet upon arrival at a network link is greater than x, and equal to zero otherwise, comprising computing a time average of a variable I(V(t)>x), said variable I(V(t)>x) equal to unity if V(t), a virtual delay of a packet upon arrival at the network link at a time t, is greater than the parameter x, and equal to zero otherwise.

23. A method of approximating an expectation value, E(I(W^{d}>x)), of a variable I(W^{d}>x) that depends on a parameter x as in claim 22 , further comprising approximating said expectation value according to $E\ue89e\left(I\ue89e\left({W}^{d}>x\right)\right)\approx \frac{1}{\rho \ue89e\text{\hspace{1em}}\ue89et}\ue89e{\int}_{0}^{t}\ue89eI\ue89e\left(V\ue89e\left(s\right)>x\right)\ue89e\text{\hspace{1em}}\ue89e\uf74cs.$

Description

This application relates to the field of computer network performance and more particularly to estimating data delays that packets encounter as they are routed through a network.

As IP networks move toward improving quality of service, Internet service providers (ISP) have been including quality of service into their service level agreements with customers. The quality of service in service level agreements may include network availability and reachability. ISPs may also include end-to-end delay benchmarks within their network into service level agreements. Such benchmarks may allow ISPs to provide better services to existing applications, such as Web browsing, as well as to new emerging services such as IP telephony and e-commerce, by providing guarantees of achieving such benchmarks.

The ability to measure quality of service may be critical to ensure that the network delivers the performance that the service level agreement promises. Measurement tools may monitor the network for compliance with the service level agreement, and identify where the provider needs to allocate more network resources.

The ability to measure quality of service may be critical to ensure that the network delivers the performance that the service level agreement promises. Measurement tools may monitor the network for compliance with the service level agreement, and identify where the provider needs to allocate more network resources.

Probe packets may be used to measure delays. Probe packets are packets that an experimenter injects into the network with the intention of measuring some aspect of their behavior, such as delay. Although probe packets could be actual user data packets, typically they are not because the experimenter wants to control the probes behavior more fully than the user's application would permit. For example, the experimenter might wish to prescribe exactly when probes are transmitted or to set the packets sizes. The experimenter might want to make the packets as small as possible to minimize their usage of network resources. Injecting probe packets into a network involves the routine use of standard networking utilities available on any PC or workstation.

One technique for estimating benchmarks related to end-to-end data traffic delay is to send small probe packets and measure their delays. For example, the Internet utility “Ping” measures the delays that the probe packets experience as they travel from one network location to another. One-way delay measurements require the clocks at the two endpoints to be synchronized, but round trip delay measurements require only that the router at the destination reflect probe packets back to the source. Many ISPs use probes to measure delay performance within their networks. Some commercial companies use probes to measure and compare different ISP network performance.

To determine what probes really measure, account may have to be made for the fact that probes and data may “see” different delay distributions because they arrive differently to a queuing system. Data traffic might be bursty, causing a later arrival to “see,” and be delayed by, an earlier data packet. Probes may see the effects of data traffic burstiness differently.

To determine how well probes measure delays, account may have to be made for sampling error, which arises since only finitely many probes in a given time interval are obtained.

By sampling from various distributions, ensemble averages of various quantities of interest such as average delay time, may be obtained. As is common in ergodic theory, conditions may be examined under which these ensemble averages are approximated by time averages. For example, Ping samples periodically (one probe every x seconds). But it may be difficult to estimate how accurately periodic sampling approximates the time average.

Even if these time averages could be accurately estimated by ensemble averaging, there remains the question of how to relate these averages obtained by using probe packets to averages involving data packets. In the prior art, practitioners may erroneously assume that the delays obtained by using probe packets are the same delays that would be experienced by data packets once sampling error is accounted for. Because obtaining probe information may be easier than obtaining data information, there is motivation to invent a method and system to convert information about probe packet delays into data delays.

The aforementioned problems may be addressed by correctly translating probe delays into data packet delays. For this purpose, a time average may be used as an intermediate quantity to pass from probe delays to data delays. Two parts may be considered. 1) Probe packets are transmitted according to the departure statistics governing a Poisson process; as described in more detail in the Detailed Description below, the user is able to estimate the time average from the probe delays with a prescribed accuracy. 2) The time average may then be related to the data packet delays. The second part is independent of the method used to obtain the time average. Thus, part 1) provides an improved estimate if the time average of the latter is of interest in another application and part 2) translates between time averages and data delays if techniques other than those in part 1) are used to estimate the time average. As an example of part 1), a better estimate of a time average, such as the fraction of time a resource is busy, may be obtained using Poisson sampling instead of periodic sampling. On the other hand, if periodic sampling were used to estimate a time average delay, the methods under 2) could still translate the time average estimate into data delay estimates.

More specifically, a method of estimating data delays in transmitting data packets from a first location to a second location on a computer network is presented including identifying a bottleneck link in a path connecting the first location to the second location; determining a queuing delay of probes at the bottleneck link by injecting probe packets at the first location; and estimating a queuing delay of data from the queuing delay of probes at the bottleneck limit.

The method of estimating data delays may further include adding a sum of data service times and a propagation delay to the queuing delay to obtain an estimate of the data delays. Determining a queuing delay of probes at the bottleneck link by injecting probe packets at the first location may include subtracting a sum of probe service times and a propagation delay from first location to second location probe delays.

Determining a queuing delay of probes at the bottleneck link by injecting probe packets at the first location may include injecting probe packets according to a probability distribution, which may include a Poisson distribution.

The method may further include determining a data packet length distribution served by the bottleneck link.

A method of estimating data delays in transmitting data packets from a first location to a second location on a computer network is also provided. The method includes transmitting probe packets on the computer network; determining probe delays for the probe packets to travel from the first location to the second location; estimating a time average from the probe delays with a prescribed accuracy; and relating the time average to the data delays.

Transmitting probe packets on the computer network may include transmitting probe packets on the computer network from the first location to the second location. Transmitting probe packets on the computer network from the first location to the second location may include transmitting probe packets on the computer network from the first location to the second location according to departure statistics consistent with a stochastic process.

Transmitting probe packets on the computer network from the first location to the second location includes transmitting probe packets on the computer network from the first location to the second location according to departure statistics consistent with a Poisson process.

A system is also provided for estimating data delays in transmitting data packets from a first location to a second location on a computer network including a computer; instructions for the computer for identifying a bottleneck link in a path connecting the first location to the second location; instructions for the computer for determining a queuing delay of probes at the bottleneck link by injecting probe packets at the first location; and instructions for the computer for estimating a queuing delay of data from the queuing delay of probes at the bottleneck limit.

The system may further include instructions for the computer for adding a sum of data service times and a propagation delay to the queuing delay to obtain an estimate of the data delays.

Instructions for determining a queuing delay of probes at the bottleneck link by injecting probe packets at the first location may include instructions for subtracting a sum of probe service times and a propagation delay from first location to second location probe delays. Instructions for determining a queuing delay of probes at the bottleneck link by injecting probe packets at the first location may include instructions for injecting probe packets according to a probability distribution, which includes a Poisson distribution. The system may further include instructions for determining a data packet length distribution served by the bottleneck link.

A system is provided for estimating data delays in transmitting data packets from a first location to a second location on a computer network. The system includes a computer; instructions for the computer for transmitting probe packets on the computer network according to departure statistics consistent with a stochastic process; instructions for the computer for determining probe delays for the probe packets to travel from the first location to the second location; instructions for the computer for estimating a time average from the probe delays with a prescribed accuracy; and instructions for the computer for relating the time average to the data delays. The stochastic process may include a Poisson process.

Also provided is a method of approximating a time average of a time-dependent variable, V, the variable representing a virtual delay of a packet upon arrival at a network link at a time t, including sending N probe packets to the data link; recording a time of arrival, A_{k}, where k≦N, of each of the N probe packets at the data link; calculating a sum of V(A_{k}), from k=1 to k_{max}, where k_{max}, and only k_{max }of the N probe packets arrive at the data link before or at the time t; calculating an expectation value of a number of packets to arrive at the data link; calculating an estimator, Z(t), given by the quotient of the sum and the expectation value of a number of packets; and approximating the time average by the estimator by bounding a variance of a difference between the estimator and the time average, the variance given by an expectation value of a time average of V(t)^{2 }divided by the expectation value of a number of packets.

Also presented below is a method of approximating a time average of a time-dependent variable V, the time average given by

where V represents a virtual delay of a packet upon arrival at a network link at the time t, including sending N probe packets to the data link so that a first of the N probe packets arrives at time A_{l}, a second at time A_{2}, a third at time A_{3 }, . . . , and an Nth at time A_{N}, where the times A_{1}≦A_{2}≦A_{3}≦ . . . ≦A_{N }are consistent with a Poisson process of rate λ_{p}; calculating an estimator Z(t), given by

where k_{max}=max{k|A_{k}≦t}; and approximating the time average by Z(t) by bounding a variance of a difference between Z(t) and the time average, the variance given by an expectation value of

For a variable I(V(t)>x) that depends on a time t and a parameter x, a method is also presented below of approximating a time average of the variable I(V(t)>x), the variable I(V(t)>x) equal to unity if V(t), a virtual delay of a packet upon arrival at a network link at a time t, is greater than the parameter x, and equal to zero otherwise, including sending N probe packets to the data link; recording a time of arrival, A_{k}, where 1≦k≦N, of each of the N probe packets at the data link; calculating a sum of I(A_{k}>x), from k=1 to k_{max}, where k_{max}, and only k_{max}, of the N probe packets arrive at the data link before or at the time t, and I(A_{k}>x) is equal to unity if A_{k }is greater than the parameter x, and equal to zero otherwise; calculating an expectation value of a number of packets to arrive at the data link; calculating an estimator, Z(t), given by the quotient of the sum and the expectation value of a number of packets; and approximating the time average by the estimator by bounding a variance of a difference between the estimator and the time average, the variance given by an expectation value of a time average of I(V(t)>x)^{2 }divided by the expectation value of a number of packets.

A method is also presented below of approximating a time average of a variable I(V(t)>x) that depends on a time t and a parameter x, the time average given by

where the variable I(V(t)>x) is equal to unity if V(t), a virtual delay of a packet upon arrival at a network link at a time t, is greater than x, and equal to zero otherwise, including sending N probe packets to the data link so that a first of the N probe packets arrives at time A_{1}, a second at time A_{2}, a third at time A_{3}, . . . , and an Nth at time A_{N}, where the times A_{1}≦A_{2}≦A_{3}≦ . . . ≦A_{N }are consistent with a Poisson process of rate λ_{p}; calculating an estimator Z(t), given by

where k_{max}=max{k|A_{k}≦t} and I(A_{k}>x) is equal to unity if A_{k }is greater than the parameter x, and equal to zero otherwise; and approximating the time average by Z(t) by bounding a variance of a difference between Z(t) and the time average, the variance given by an expectation value of

A method is also presented below of approximating an expectation value, E(W^{d}), of a delay experienced by a data packet arriving at a network link, including computing a time average of a time-dependent variable, V(t), the variable representing a virtual delay of a packet upon arrival at the network link at a time t, where the time average is given by

computing an expectation value, E(U), of a packet size; computing an expectation value, E(U^{2}), of a square of the packet size, utilizing the time average, the expectation value of a packet size, the expectation value of a square of the packet size, and a server utilization, ρ, to approximate the expectation value of a delay.

Utilizing the time average, the expectation value of a packet size, the expectation value of a square of the packet size, and a server utilization, ρ, may include utilizing the time average, the expectation value of a packet size, the expectation value of a square of the packet size, and a server utilization, ρ, to approximate the expectation value of a delay according to

A method is also presented below of approximating an expectation value, E(I(W^{d}>x)), of a variable I(W^{d}>x) that depends on a parameter x, the variable I(W^{d}>x) equal to unity if a delay of a data packet upon arrival at a network link is greater than x, and equal to zero otherwise, including computing a time average of a variable I(V(t)>x), the variable I(V(t)>x) equal to unity if V(t), a virtual delay of a packet upon arrival at the network link at a time t, is greater than the parameter x, and equal to zero otherwise.

The last method may further include approximating the expectation value according to

A method is also presented below of estimating data delays in transmitting data packets from a first location to a second location on a computer network including identifying a bottleneck link in a path connecting the first location to the second location; estimating a queuing delay of data from a queuing delay of probes at the bottleneck limit; and adding a sum of data service times and a propagation delay to the queuing delay to obtain an estimate of the data delays.

A system is also presented below for estimating data delays in transmitting data packets from a first location to a second location on a computer network including a computer; instructions for the computer for identifying a bottleneck link in a path connecting the first location to the second location; instructions for the computer for estimating a queuing delay of data from a queuing delay of probes at the bottleneck limit; and instructions for the computer for adding a sum of data service times and a propagation delay to the queuing delay to obtain an estimate of the data delays.

The system may further include instructions for determining a data packet length distribution served by the bottleneck link.

The following figures depict certain illustrative embodiments of the invention in which like reference numerals refer to like elements. These depicted embodiments are to be understood as illustrative of the invention and not as limiting in any way.

FIG. 1 illustrates an embodiment of a system for network traffic collection;

FIG. 2 illustrates an embodiment that depicts a simulation configuration;

FIG. 3 illustrates a plot of user datagram protocol (UDP) packets roundtrip delay tail distributions;

FIG. 4 illustrates showing a packet arrival process;

FIG. 5 illustrates a plot relating the virtual and actual mean delays;

FIG. 6 illustrates a plot relating the virtual and actual delay tails;

FIG. 7 illustrates a plot showing the data queuing delay tail estimation;

FIG. 8 illustrates an embodiment of a network depicting the delay of interest;

FIG. 9 illustrates depicting a queuing model;

FIG. 10 illustrates a flow chart summarizing the steps involved in obtaining data delays from probe delays;

FIG. 11 illustrates a plot of end-to-end data delay tails; and

FIG. 12 illustrates possible origin and destination configurations.

To provide an overall understanding of the invention, certain methods, and systems will be discussed with reference to estimating data delays from Poisson probe delays. However, it will be understood by persons of ordinary skill in the art that the general methods, and systems described herein are equally applicable to all cases in which probe delays are used nontrivially to estimate data delays. Principles of the invention described below may be applied to applications in which data delays are ascertained on a computer network.

It is often assumed that probe packet queuing delay statistics (e.g., mean, cumulative distribution) are the same as data packet statistics, except for sampling error. Thus, it is widely believed, sending more probes during a measurement period would reduce any discrepancy. The following examples show that probe and data statistics may not be the same.

In FIG. 1, an example of an embodiment of a system for network traffic collection is shown. A monitoring point II is shown installed at a local area network (LAN) **13**. A traffic monitoring tool **12** is used at this monitoring point **11** to capture Internet traffic entering and leaving the LAN **13** through a 10 Mbps link. An example of a traffic monitoring tool **12** is EtherPeek™, a commercially available software package of The AG Group, Walnut Creek, Calif., which may be run on a PC. Other traffic monitoring tools **12** may also be used. Traffic traces containing a sequence of IP packet arrival times (accurate to the microsecond), packet lengths, source and destination addresses, and protocols may be collected. A public Internet router **14** and a LAN router **15** service network traffic in the public Internet **16** and LAN **13** areas. Routers **14** and **15** are devices which forward packets between networks. The forwarding decision by routers **14** and **15** may use network layer information and routing tables, as may be constructed by routing protocols.

Downstream packets (those that enter the local area network **13**) are separated from upstream packets (those that leave the local area network **13**) according to packet source and destination addresses. Downstream traffic includes mainly web page downloads while upstream traffic includes mainly short request and acknowledgment packets. In an embodiment, there may be more downstream traffic (about 1.6 Mbps) than upstream (0.69 Mbps) traffic.

A router such as **14** and **15** that processes the downstream traffic together with a stream of (independent and identically distributed) exponentially spaced probes may be simulated using simulation software. In one embodiment, OPNET, a simulation package available from MIL 3 Incorporated, Washington, D.C., may be used for the simulation. Assuming that packet delays at the LAN router **15** include mainly queuing and transmission delays at the outgoing link, the analysis of packet delays at the LAN router **15** reduces to the analysis of the delays at a single queue. It may be further assumed that the outgoing link serves packets in a first-in-first-out (FIFO) order.

FIG. 2 is an example of an embodiment that depicts a simulation configuration at a FIFO queue **21** that may be present at a router. The FIFO queue **21** simulates the router's outgoing link **22**. Two streams feed the link **22**: collected Internet traffic data packets **23** and probe packets **24**. The probe packets **24** are 64 bytes long and arrive at an average rate of one probe packet per second. The service rate of the FIFO queue **21** may be varied to achieve different link utilizations.

Table 1 shows the average queuing delays, i.e., not including transmission delays, for data packets **23** and probe packets during a 20-minute measurement interval. The “percentage error” in the fourth column is defined as (Mean Probe Queuing Delay−Mean Data Queuing Delay)÷Mean Data Queuing Delay. A negative percentage error indicates that the mean probe queuing delay underestimates the mean data queuing delay. It does so consistently, by 22% to 54%.

TABLE 1 | |||||

Estimating mean data queuing delays from mean probe delays | |||||

Com- | |||||

Mean Data | Mean Probe | puted | |||

Link | Queuing | Queuing | Per- | Data | |

Utili- | Delay | Delay | centage | Queuing | Percentage |

zation | (ms) | (ms) | Error | (ms) | Error |

30% | 2.68 | 1.24 | −53.77% | 3.19 | 18.9% |

35% | 4.30 | 2.10 | −51.12% | 4.91 | 14.08 |

40% | 7.01 | 3.44 | −50.95% | 7.34 | 4.67% |

45% | 11.33 | 5.78 | −49.01% | 11.42 | 0.79% |

50% | 18.29 | 10.65 | −41.77% | 19.72 | 7.79% |

55% | 29.54 | 19.34 | −34.52% | 33.40 | 13.08 |

60% | 47.79 | 33.74 | −29.41% | 54.28 | 13.57 |

65% | 78.90 | 56.93 | −27.84% | 85.42 | 8.27% |

70% | 153.56 | 119.24 | −22.34% | 167.88 | 9.33% |

The observations above may be further validated with an experiment involving two computers on the Internet. Host A is at GTE Labs, Waltham, NIA and host B is at Needham, Mass. During the experiment, host A sends out user datagram protocol (UDP) packets to host B. In turn, host B simply reflects those packets back to host A. In one embodiment, the Snoop utility, available on Unix workstations, may be used at host A to measure packet round-trip delays. To minimize delays introduced by the hosts, there are no other application programs running at the hosts during the measurement period.

Host A is programmed to send out two streams of UDP packets. The first is a Poisson packet stream of rate one packet per second (the “probe” steam). The second stream (the “data” stream) contains bursts of packets. The number of packets in a burst is uniformly distributed between one and eight packets. The inter-burst arrival time is also uniformly distributed between 0 and 270 ms. All the UDP packets are 1000 bytes long.

In FIG. 3 is an example of a plot of user datagram protocol (UDP) packets round-trip delay tail distributions. The data stream curve **31** and the probe stream curve **32** are the probabilities of the delay being greater than a particular time versus that time for the data and probe packets respectively. Since all the UDP packets are of the same length, it may be expected that the two streams of packets have the same round-trip delay statistics. However, as can be seen by comparing curves **31** and **32**, the probe stream may experience lower delays. In a particular 20-minute measurement interval, the average round trip delays are 68 ms for the probe stream and 76 ms for the data stream. These results are consistent with those of Table 1.

Discrepancies in delays between probe and data packets may be explained. Momentarily neglecting sampling error, Poisson arrivals see time averages, or “PASTA” (R. Wolff, Poisson arrivals see time averages, *Operations Research, *Vol. 30, No. 2, March-Aprril, 1982) may be invoked to assert that the mean probe delay equals the time average delay. A discrepancy then arises between the time average and the data delay. The discrepancy occurs because the bursty data arrival process does not sample the idle link as often as idleness occurs in time.

FIG. 4 illustrates a packet arrival process. In FIG. 4, probe packets **41** are of small constant length and arrive according to a Poisson process. Data packets **42** come in pairs and both packets are of the same constant length. Each utilizes r units of service time. The time between successive arrivals of pairs is a fixed quantity T and ρ=2r/T is the link utilization, assumed to be less than one.

Ignoring the effect of probes, the first packet of a pair does not wait for service, while the second packet has to wait r units of time before being transmitted. The average data packet queuing delay is then 0.5 r regardless of the link utilization.

In addition, by PASTA, a fraction 1-ρ of probe packets incurs no delay, while a fraction of probes experiences an average of r units of queuing delay, making the average probe delay ρr. The ratio of mean probe delay to mean data delay is 2ρ. The ratio ranges from 0 to 2, so probe delays can be larger or smaller than data delays.

In accordance with principles of the present invention, data delays are estimated by (1) approximating the time average by the sample statistics and (2) approximating data packet statistics by time averages. The second step is independent of the way the time average is estimated and so applies to exponential, periodic, or another technique that gives an estimate of the time average.

A router is modeled in an IP network. The outgoing link is the bottleneck in the router: packet delays at the router mainly include queuing and transmission delays at the outgoing link. Delays in other parts of the router, e.g., routing table lookups, are negligible. Service on the link is first-in first-out (FIFO). The router is represented by a single server FIFO queue with effectively infinite waiting room (effectively infinite because loss behavior is not studied). The queue receives two packet streams, data and probes, and, except where noted below, the notation refers to the aggregate stream. The following notation is used below.

V(s) is the virtual delay at the link at time s, i.e., the delay an arrival at time s would see or the total number of bits in a queue at time s (including the bits of the packet in service) divided by the link speed.

T_{n }is the time between packet arrivals n and n+l. Packets include data and probes.

A_{n }is the time when the nth packet arrives. A(t) is the total number of packets that arrive in the interval [**0**,t].

U_{n }is the size (in seconds) of the nth packet to arrive.

W_{n }is the delay that the nth arrival sees, i.e., the virtual delay at the arrival time, which does not include U_{n}.

N(t) is the number of probes that arrive in the interval [**0**,t]. We assume N is a Poisson process with rate λ_{p}. Probe packets are of constant size.

The following assumptions may be made below.

Assumption 1. A(t)/t converges almost surely to a limit λ as t →∞,

Assumption 2. For each n, the packet service U_{n }is independent of {U_{k , T} _{k}:k<n} and the U_{n }are identically distributed.

Assumption 3. The sequence {(T_{n}, U_{n})} is stationary and ergodic.

The actual delay process {W_{n}:n≧0} evolves according to Lindley's equation (S. Asmussen, *Applied Probability and Queues, *New York: John Wiley & Sons, 1987):

*W* _{n+1}=(*W* _{n} *+U* _{n} *−T* _{n})^{+}.

Also, W_{n}=V(A_{n}−) and V increases by the amount U_{n }at time A_{n }and decreases with slope −1 on each interval [A_{n}. A_{n+1}] while V **22** 0. Whenever V becomes zero, it stops decreasing and remains at zero until the next increase.

The difference between the delays that the probes sample and the corresponding time average delays may be analyzed. Some of the results presented below may not require Assumptions 1, 2, or 3. Let f be a bounded, measurable function and U(s)=f(V(s)). Two examples are f(v)=v (when estimating means; to make f bounded, it may be truncated, for example, at the buffer size) and f(v)=I(v>x) (when estimating tails), where I is an indicator function (**1** if its argument is true, and **0** otherwise). It may be assumed that U has left continuous sample paths and right-hand limits (R. Wolff, 1982). Wolff's Lack of Anticipation Assumption (LAA) may also be assumed: For each s>0,{N(s+u)−N(s):u≧0} and {U(x): 0≦×≦s} are independent.

The quantities Y(t), and Z(t), may be defined as follows:

By the left continuity of U, Y(t) is the sum of the values of U immediately before the probe arrival epochs. The mean of N(t) instead of N(t) itself appears in the denominator of Z(t). This choice makes the analysis of the variance tractable and avoids the event {N(t)=0}.

Probe measurements over the time interval [**0**,t] provide the estimator Z(t), while the time average is the random variable (not a constant, as in traditional sampling)

For example, when f(v)=v, the time average is the virtual delay averaged over the measurement interval (**0**,t). When f(v)=I(v>x), the time average is the fraction of time the virtual delay exceeds x.

The quantity R(t) may be defined as

(R. Wolff, 1982). It then follows that:

measures the difference between the estimator and the time average. By Eq.(3) of the last reference, E(R(t))=0, i.e., the estimator Z(t) is unbiased. The orthogonal increments property (D. Williams, *Probability with Martingales, *Cambridge, Cambridge University Press, 1991, Chapter 12) of the martingale N(s)−λ_{p}s may be used to calculate the variance R(t).

Lemma: Under LAA,

Proof. For integral n>0, define

Then R_{n}(t)→R(t) pointwise and when f is bounded by a constant M, R_{n}(t) is bounded by the function MN(t), which is square integrable. By dominated convergence,

Write

where the sum on the right has two parts: the “diagonal” terms of the square, and S, the sum of n(n−1) “off-diagonal” terms. The expectation of a typical summand in S takes the form

*E{U*(*jt/n*)*U*(*kt/n*)(*N*((*j+*1)*t/n*)−*N*(*kt/n*)−λ_{p} *t/n*)}×*E{N*((*k*+1)*t/n*)−*N*(*kt/n*)−λ_{p} *t/n}=*0

where j<k. The expectation of the product of the four terms is the product of the expectations shown above by the LAA and the independent increments property of the Poisson process. The right-hand expectation is zero since the Poisson process N has rate λ_{p}. Thus, E(S)=0. Using LAA and E[N((k+1)t/n)−N(kt/n)−λ_{p}t/n]^{2}=λ_{p}t/n on the diagonal terms,

Dominated convergence gives the result. (See also, D. D. Yao, On Wolff's PASTA Martingale, Operations Research, Vol. 40, 1992).

By the lemma,

The independent increments property of the Poisson may be used as a simplifying property. Under exponential sampling, the variance is the same as it may be if the samples were independent. If the sampling does not affect the observed process, then U remains the same as λ_{p }is changed. Var R(t)/(λ_{p}t) then decreases inversely in λ_{p}t. In practice, this may be achieved by not sampling too often.

Let f(v)=I(v>x). Then U(s)=I(V(s)>x)=U(s)^{2}. Assuming V is stationary,

With an a priori bound on P(V>x), the variance can be bounded.

When f(v)=v (or a truncated version) and V is stationary.

For example, if V<0.5 and λ_{p}t≈1000, then the variance is at most 0.00025.

Having just quantified the discrepancy between the ensemble and time averages of the probe delays by approximating the variance of R(t)/(λ_{p}t), the time average is now approximated to the ensemble average of data delays. By association, a relationship between probe and data delays will thus be obtained.

The two averages

are related asymptotically by generalizations of Little's law (S. Brumelle, On the relation between customer and time averages in queues, *J Appl Prob., *Vol. 8, 1971; S. Asmussen, *Applied Probability and Queues, *New York: John Wiley & Sons, 1987, VIII.3.4).

In FIG. 5 appears an example of a plot relating the virtual and actual mean delays. The area under V on the interval [**0**,t] is divided into right triangles of height U_{n} **51** and parallelograms of height W_{n }and base U_{n } **52** (S. Asmussen, 1987). An error V(**0**)^{2}/2**53**, and another error V(t)^{2}/2 **54** occur at both the left and right endpoints, respectively, leading to the expression

By Assumption 3, the error terms are o(t) (S. Asmussen, 1987). Hence, by applying Assumptions 1 and 3,

where the expectations of random variables without subscripts correspond to limiting distributions (R. M. Loynes, The stability of a queue with non-independent inter-arrival and service times, *Proc. Camb. Philos. Soc., *Vol. 58, 1962). By Assumption 2,

for large t, where ρ=λE(U) is the server utilization. Then

The probe packet rate may be much smaller than the data packet rate so that probe packets do not consume too many resources, such as computer time. Assuming that the mean data rate satisfies λ_{d}>>λ_{p }it follows that E(W)=λ_{d}/λE(W^{d})+λ_{p}/λE(W^{p})≈E(W^{d}), so the preceding expression is approximately the mean data delay. Here, the superscripts d and p signify data and probes, respectively.

Instead of the mean delay, delay tails may be examined. The development parallels that in the preceding paragraph.

FIG. 6 illustrates a sample path of V. The fraction of W_{n}, that exceeds the level x during the interval [**0**,t] is of interest. The starting expression is

Here, l=[A_{1}−(x−W_{1})^{+}]^{+} and r=[(W_{A(t)}+U_{A(t)}−x)^{+}−(t−A_{A(t)})]^{+} are the left-hand error **61** and right-hand error **62** in FIG. 6. I_{n }is the contribution of the nth arrival to the integral on the left-hand side:

or

*I* _{n} *=U* _{n} *I*(*W* _{n} *≧x*)+(*W* _{n} *+U* _{n} * 31 x*)

The error terms are again o(t); using Assumptions 1 and 3, it may be seen that

where P(V>x)=λE(I) is the limit. The calculation of E(I) may be broken up into two steps.

Lemma 1. Under Assumption 2,

*E*(*U* _{n} *I*(*W* _{n} *≧x*))=*E*(*U* _{n})*P*(*W* _{n} *>x).*

Proof. Assumption **2** implies that U_{n }and W_{n }are independent.

For the next result, the so-called residual or excess lifetime associated with the random variable U_{n }may be used. Wherever convenient, the subscript n is omitted. If B is the distribution function of U_{n}, then the residual lifetime of U* has distribution function

Lemma 2. Under Assumption 2,

*E*[(W_{n} *+U* _{n} *−x*)*I*(W_{n} *≦x<W* _{n} *+U* _{n})]=*E*(*U*)*P*(*W≦x<W+U*).*

Proof. Recalling that subscripts have been omitted, for w≦x, the conditional expectation

The third line results from integration by parts. The result follows.

Proposition. Assume that the U_{n }are bounded above by a constant m and that Assumption 2 holds. Then

^{−1} *P*(*V>x+m*)≦*P*(*W>x)≦ρ* ^{−1} *P*(*V>x*)

Proof. By the two lemmas, P(V>x)=ρP(W+U*>x)≧ρP(W>x). Since

*U*≦m, ρP*(*W>x*)≦*P*(*V>x*)≦ρ*P*(*W>x−m*).

The result follows by using both inequalities.

This result allows the estimation of the tails of the distribution of W in terms of the tail of V. As in the preceding section, the distribution of W represents the data packet delay distribution, since probe traffic is relatively negligible. The tail of W is confined to an interval of length at most ρ^{−1}P(x<V<x+m). If x is large compared to m, then it may be expected that ρ^{−1}P(x<V<x+m), and |P(V>x)−ρP(W>x)|, which is less than or equal to P(x<V<x+m), are small.

As an example, suppose V has an exponential tail or an exponential bound (as provided by large deviations, for example): P(V>x)=e^{−αx}. Then

*P*(*x<V<x+m*)=*e* ^{−αx}(1−*e* ^{−αm})≈*e* ^{−αx} *αm *

The relative error in the estimates is then

Suppose that an overflow from a buffer size x is to be made improbable: P(V>x)=e^{−αx}=ε<<1.

Then αx=log (1/ε), and the relative error is approximately

*m=mx* ^{−1}log(1/ε)

For example, if ε=10^{−6}, then log 1/ε≈14 and the relative error becomes 14m/x. On the other hand, if ε=10^{−2}, then log (1/ε)≈5. If the buffer can hold 100 maximal size packets, the error in the latter case is at most 5%.

The use of the above approximations, along with the errors committed in estimating tail probabilities, is now discussed. During a measurement interval [**0**,t], N(t) probe delay measurements are collected, and the estimator

is formed. By using an estimate, Z(t) may be related to the fraction of data packets whose delay exceeds x; part of the error in the estimate may be controlled through intermediate approximations:

By selecting a high enough sampling rate λ_{p}, both sides of the first approximation may be made small in the mean square sense (i.e., the variance). The second and fourth approximate equalities correspond to almost sure pointwise limits in the ergodic theorem; the quality of these approximations cannot be controlled, Nor may the error in the third approximate equality, which results from Assumption 2, be controlled. What may be controlled is the accuracy of the last approximation by showing that ρP(W≦x<W+U*) is small, as above. The final source of error comes from assuming that probes have a negligible effect (e.g., W=W^{d}). This may be controlled if the data arrival rate λ_{d }is known. Assuming probes have a negligible effect also yields P(W>x)=E(I(W^{d}>x)).

The mean data packet delay predicted by Eq. (1) may be compared to the simulation results in Table 1. The column labeled “Computed Data Queuing” is the result of substituting the mean probe queuing delay for the time average in Eq. (1). Using these values in accordance with principles of the current invention, instead of the mean probe queuing delays as estimators, reduces the errors. When the link utilization is above 50%, the estimator is at most 15% above the true value. In comparison, the mean probe queuing delay ranges from 20% to 40% below the true values.

The packet service times in some traces may be correlated, so Assumption 2 does not hold. Nonetheless, our methods give good agreement with the simulation results. In particular, if the packet sizes, and the U_{n }are constant, then the same results would follow as with independence. Files transferred across the Internet are typically segmented into some number of “maximum segment size” packets (of equal size) plus a remainder packet, so the constant size assumption may be reasonable.

FIG. 7 shows the estimated delay tail distribution in relation to the bounds described by Equation (2). The solid curve is the data packet delay curve **71**, the dashed curve the estimated lower bound curve **72**, and the remaining curve the estimated upper bound curve **73**. For the same reasons listed above, the data packet distribution does not fit Equation (2) exactly. The bounds are, however, close to the real data queuing delay distribution.

Extending the single node, one queue results discussed above to networks having multiple nodes may now be set forth in the following paragraphs. Probe packets pass through a sequence of nodes along their path through the network. The first effect of multiple nodes is to eliminate the conditions that PASTA requires. Even if probes arrive in a Poisson stream to the first node along the path, their arrivals to subsequent nodes may not be Poissonian. To see this explicitly, denote by τ_{n }the time when the nth probe packet arrives to the first node. Then the nth probe will arrive at the second node at time

_{n} *+V*(τ_{n})+*d,*

where V is the virtual delay function at the first node and d is the propagation delay between nodes **1** and **2**. A similar relationship holds between the probe arrival times at any pairs of adjacent nodes. If the V(τ_{n}) are not constant, then the process τ_{n}+V(τ_{n})+d might not be Poissonian.

In contrast, adding a constant offset to a Poisson process preserves the Poisson property. If it is assumed that a single bottleneck node occurs along the probe's path, and that packets experience essentially no delay at nodes other than the bottleneck, V(τ_{n}) equals the probe service time, which is constant. The same holds true at other non-bottleneck nodes. Thus, the probes arrive in a Poisson stream to the bottleneck.

Another consequence of passing probes through nodes in tandem is that LAA may fail. In addition, the service times U_{n }and the waiting times W_{n }are negatively correlated—not independent—at nodes other than the first (R. Wolff, 1982). As a result, Assumption 2 cannot hold and Lemma 1 becomes E(U_{n}I(W_{n}≧x))≦E(U_{n})P(W_{n}>x).

Multiple nodes may also lead one to account for propagation delays and service times at all the nodes. Suppose the path the probes follow traverses n links, with transmission speeds c_{1}, . . . , c_{n}, and that the total propagation delay is D. The sum of the link service times of a packet of length x is γx, where γ=1/c_{1}+ . . . +1/c_{n}. Consider a typical probe packet of length L^{p }(subscripts are omitted in the following). It experiences an end-to-end delay

*W*
_{ee}
^{p}
*=V+γL*
^{p}
*+D,*

where V is the probe delay at the bottleneck node and no delays at other nodes are assumed. The notation V intentionally suggests that the probes see time averages. Similarly, a data packet's end-to-end delay may be given by

*W*
_{ee}
^{d}
*=W+γL*
^{d}
*+D,*

where W is its delay at the bottleneck node.

Probe measurements give the distribution Of W_{ee} ^{p}. Given γ, the distribution of V may be obtained because γL^{p}+D is a constant, as a result of the fixed probe size. The results above then give the distribution of W. If L^{d }were not random, the distribution W_{ee} ^{d }would be known. If γ is large (i.e., some link other than the bottleneck is slow), W_{ee} ^{d}−D=W+γL^{d }is the sum of two random variables, which may be comparable in size. In this case, the service time may be separated out at the bottleneck and Assumption 2 invoked again. The distribution of the sum is then a convolution, which may be calculated numerically. If the bottleneck is significantly slower than all the other links, L^{d }may be replaced with its mean or a percentile, incurring a small error.

Estimating end-to-end mean data packet delays is similar. Equation (1) may be invoked to pass from E(V) to E(W). Then

*E*(*W* _{ee} ^{d})=*E*(*W*)+γ*E*(*L* ^{d})+*D* (3)

Knowledge of E(L^{d}), together with other principles consistent with the present invention, may be used to calculate E(W_{ee} ^{d}).

An end-to-end delay analysis may require knowledge of link speeds, the data packet length distribution, and the bottleneck link utilization ρ. To the extent that any of these may be unavailable, they may have to be replaced by approximations. Effects such as these may require approximations to be validated on real or simulated networks.

Referring to FIG. 8, an ISP may provide one of its business customers with Virtual Private Network (VPN) services that connect the customer's headquarters office **81** to a remote office **82**. The headquarters office **81** is connected to the ISP via the headquarters office point of presence (POP) router **83** and the remote office **82** is connected to the ISP via the remote office POP router **84**. These two routers are connected by an ISP backbone router **85**.

Suppose that the ISP is interested in estimating the one-way data packet delay from the headquarters office POP router **83** to the remote office POP router **84**. Probes heading to the remote office **82** may be generated on a PC **89**, injected into the headquarters office POP router **83**, and captured at the output of the remote office POP router **84**. Assuming that clocks are properly synchronized, the end-to-end probe delays may be measured correctly.

To apply the theories developed in the previous sections to estimate data packet delays from the probe end-to-end delays, the ISP may need to first identify the bottleneck link. The ISP already knows the bandwidth of a left link **86**, middle link **87**, and right link **88** in FIG. **8**. The link utilization during the period of interest may be obtained from simple network management protocol (SNMP) management information bases (MIB) on the routers. Suppose that during the period of interest, the right link **88** has a much higher utilization than either the left link **86** or middle link **87**, and hence is the bottleneck link. Next, the ISP may need to know the data packet length distribution served by the bottleneck link during the period of interest. It may be estimated through sampling, or by past experience.

FIG. 9 is an example depicting a queuing model that may be subjected to the principles consistent with the present invention to determine queuing delays. A queuing model of the path with a first **93**, second **96**, and third **99** queue, and a first **94**, second **97**, and third **100** link is shown. The three queues may model the three router output links respectively. A probe stream **91** carries packets that are launched according to a Poisson distribution of average rate one probe per second. The probe packets are 64 bytes long. In addition, there are two traffic streams. First queue stream **92** represents the traffic sent from the headquarters to the remote office. It enters the network at the first queue, passes through the queues in sequence and leaves the network after being processed by the third queue. The second queue arrival **95** and departure **98** streams represent all other traffic carried by the backbone link. It enters the network at the second queue **96** and leaves the network immediately after being processed by that queue.

As an example, two traffic traces collected at a facility may be used as the two data input streams and a simulation may be conducted. The service rates of the first queue **93** and second queue **96** are chosen such that the first queue **93** has 10% utilization and the second queue **96** has 5% utilization. The service rate of the third queue **99** may be varied so that its utilization ranges from 30% to 60%. As a result, the third queue **99** is the bottleneck in all the cases.

The end-to-end delays for probes, i.e., W_{ee} ^{p}, during the 20-minute period are collected from the simulation. The mean probe queuing delay may be estimated at the bottleneck queue by subtracting the sum of the probe service times at the three queues and the propagation delay from the mean end-to-end probe delay. Equation (1) may then be applied to estimate the mean data queuing delays at the bottleneck queue. Finally, as in Equation (3), the stun of the mean data service time at the three queues and the propagation delay may be added to the estimated data queuing time at the bottleneck queue to get the mean end-to-end data packet delay.

FIG. 10 is a flow chart (**1000**) summarizing the steps involved in estimating data delays from probe delays. In step **101**, a bottleneck is identified in the path leading from a first location to a second location—in the example above, from the headquarters office to the remote office. Network operators may identify the bottleneck link by inspecting link statistics collected by routers. End users may identify the bottleneck link by using the “packet pair” mechanism, as described in S. Keshav, “A control-theoretic approach to flow control,” Proc. SIGCOMM 1991, and R. L. Carter and M. E. Crovella, “Measuring bottleneck link speed in packet-switched networks,” Rept. BU-CS-96-006, Boston University, Mar. 15, 1996. In step **102**, probe packets are generated according to Poisson statistics at a PC or Unix workstation, for example, and injected into the network for delivery to the second location. Standard networking utilities on the PC or workstation may be used to inject the packets into the network. In step **103**, the mean queuing delay of the probe packets is determined. Equation (1) may then be used in step **104** to estimate the mean queuing delay of data from the mean queuing delay of probes. Finally, in steps **105** and **106**, an estimate of the data delay is obtained, by adding the mean data service times and the propagation delay to the mean queuing delay, according to Eq. (3).

In one embodiment, steps **102** and **103** may be implemented in C, and steps **104** and **105** in Matlab, C, or C++.

Table 2 shows the results and compares them with the mean end-to-end data delays collected directly from the simulation. Again, high estimation errors result if one used the mean probe end-to-end delay directly to estimate the mean data end-to-end delay. On the other hand, the approach described above produces results that are quite close to the mean data end-to-end delay collected directly from the simulation.

TABLE 2 | |||||

End-to-end data packet delay estimation. E-E: End-to-End | |||||

Link | Mean Data | Mean Probe | Per- | Computed | Per- |

Utili- | E-E Delay | E-E Delay | centage | E-E Delay | centage |

zation | (ms) | (ms) | Error | (ms) | Error |

30% | 4.20 | 1.60 | −61.90% | 4.72 | 12.29% |

40% | 8.90 | 3.90 | −56.18% | 8.82 | −0.95% |

50% | 20.50 | 11.20 | −45.37% | 21.14 | 3.10% |

60% | 50.30 | 34.40 | −31.61% | 55.70 | 10.74 |

To estimate the end-to-end data delay tails, L^{d }may be replaced with its mean as described above. FIG. 11 shows the end-to-end data delay tail estimation when the bottleneck link is 50%. The solid curve represents the data packet delay curve **111**, the dashed curve **112** the estimated lower bound curve **112**, and the remaining curve the estimated upper bound curve **113**. The bounds are reasonably close to the real data delay.

In this example, the ISP knows the bandwidth and utilization for all the links within its network. If, however, a business customer wishes to estimate the end-to-end delay, the link utilization information may be used from either the ISP or by making approximations, for example, through using various tools.

Finally, in FIG. 12 is shown various examples of origin and destination configurations that are amenable to the present invention. End-to-end delays **121**, delays between two points inside a network **122**, round trip delays from A to C to B **123** (where A and B are at the same location), end to intermediate node delays **124**, and round trip delays from A to C to B **125** (where A and B are at the same location) may all be computed using systems and methods of the present invention.

The principles consistent with the present invention admit many generalizations. For example, although stochastic processes having Poisson statistics are mentioned by name herein, other stochastic processes may be possible. For example, for the principles of the invention to hold, it is sufficient that the fraction of arrivals, in a realization of the stochastic process, that see a particular delay be equal, in the long time limit, to the time average delay. Such stochastic processes may be said to have the ASTA condition. I.e., arrivals see time averages.

Also, while time averages and ensemble averages were used above, other mathematical objects may be used to non-trivially relate probe packet delays to data packet delays.

While the invention has been disclosed in connection with the preferred embodiments shown and described in detail, various modifications and improvements thereon will become readily apparent to those skilled in the art. Accordingly, the spirit and scope of the present invention are to be limited only by the following claims.

Patent Citations

Cited Patent | Filing date | Publication date | Applicant | Title |
---|---|---|---|---|

US5408465 * | Jun 21, 1993 | Apr 18, 1995 | Hewlett-Packard Company | Flexible scheme for admission control of multimedia streams on integrated networks |

US5477531 * | May 28, 1992 | Dec 19, 1995 | Hewlett-Packard Company | Method and apparatus for testing a packet-based network |

US5946662 * | Mar 29, 1996 | Aug 31, 1999 | International Business Machines Corporation | Method for providing inventory optimization |

US6023681 * | Aug 11, 1997 | Feb 8, 2000 | At&T Corp. | Method and apparatus for predicting queuing delays |

US6115462 * | Jan 9, 1998 | Sep 5, 2000 | Gte Laboratories Incorporated | Method and apparatus for efficient call routing |

US6192406 * | Jun 13, 1997 | Feb 20, 2001 | At&T Corp. | Startup management system and method for networks |

US6215772 * | Nov 26, 1997 | Apr 10, 2001 | International Business Machines Corporation | Dynamic parameter estimation for efficient transport of HPR data on IP |

US6226266 * | Oct 7, 1997 | May 1, 2001 | Cisco Technology, Inc. | End-to-end delay estimation in high speed communication networks |

Non-Patent Citations

Reference | ||
---|---|---|

1 | D. D. Yao, On Wolff's Pasta Martingale, Operations Research 40, S352 (1992). | |

2 | D. Williams, Probability with Martingales, Cambridge University Press, 1991, Chapter 12. | |

3 | R. M. Loynes, The stability of a queue with non-independent inter-arrival and service times, Proc. Camb. Philos. Soc. 58, 497 (1962). | |

4 | R. Wolff, Poisson arrivals see time averages, Operations Research 30, 223 (1982). | |

5 | S. Asmussen, Applied Probability and Queues, New York: John Wiley & Sons, 1987, Chapt. VIII. | |

6 | S. Brumelle, On the relation between customer and time averages in quenes, J. Appl Prob. 8, 508 (1971). |

Referenced by

Citing Patent | Filing date | Publication date | Applicant | Title |
---|---|---|---|---|

US6807515 * | Sep 14, 2001 | Oct 19, 2004 | Telephia, Inc. | Wireless network monitoring |

US6937603 * | Jun 2, 2000 | Aug 30, 2005 | Intel Corporation | Optimizing buffer latency in a streamed packet delivery session |

US7120125 * | Dec 26, 2001 | Oct 10, 2006 | Fujitsu Limited | Communication capability measuring equipment |

US7239611 | Mar 3, 2003 | Jul 3, 2007 | Microsoft Corporation | Controlling admission of data streams onto a network based on end-to-end measurements |

US7286482 | Nov 29, 2002 | Oct 23, 2007 | Alcatel Lucent | Decentralized SLS monitoring in a differentiated service environment |

US7359835 | Oct 15, 2004 | Apr 15, 2008 | Andreas Vogel | Method and system for probing a wireless network to monitor and process the wireless network performance |

US7376083 * | Dec 9, 2003 | May 20, 2008 | International Business Machines Corporation | Apparatus and method for modeling queueing systems with highly variable traffic arrival rates |

US7403994 * | Aug 29, 2000 | Jul 22, 2008 | International Business Machines Corporation | Method of doing business over a network by transmission and retransmission of digital information on a network during time slots |

US7496046 * | Aug 21, 2002 | Feb 24, 2009 | Nippon Telegraph And Telephone Corporation | Packet communication quality measurement method and system |

US7545749 * | Feb 15, 2005 | Jun 9, 2009 | Microsoft Corporation | High-accuracy packet pair for network bottleneck bandwidth measurement |

US7568045 * | Jul 28, 2009 | Cisco Technology, Inc. | Method and apparatus for estimating periodic worst-case delay under actual and hypothetical conditions using a measurement based traffic profile | |

US7668096 | Feb 23, 2010 | International Business Machines Corporation | Apparatus for modeling queueing systems with highly variable traffic arrival rates | |

US7675856 * | Mar 9, 2010 | Microsoft Corporation | Bandwidth estimation in broadband access networks | |

US7675868 | Mar 9, 2010 | Avaya Inc. | Method and apparatus for coordinating routing parameters via a back-channel communication medium | |

US7720959 * | Oct 17, 2001 | May 18, 2010 | Avaya Inc. | Method and apparatus for characterizing the quality of a network path |

US7773536 | Nov 30, 2007 | Aug 10, 2010 | Avaya Inc. | Method and apparatus for the assessment and optimization of network traffic |

US7778169 * | Sep 2, 2005 | Aug 17, 2010 | Cisco Technology, Inc. | Packetizing media for a time slotted communication system |

US7778179 * | Nov 23, 2005 | Aug 17, 2010 | Telefonaktiebolaget L M Ericsson (Publ) | Using filtering and active probing to evaluate a data transfer path |

US7835886 | Nov 16, 2010 | The Nielson Company (US), LLC. | Method and system for probing a wireless network to monitor and process the wireless network performance | |

US7840704 | Jun 11, 2008 | Nov 23, 2010 | Avaya Inc. | Method and apparatus for performance and cost optimization in an internetwork |

US7852763 * | May 8, 2009 | Dec 14, 2010 | Bae Systems Information And Electronic Systems Integration Inc. | System and method for determining a transmission order for packets at a node in a wireless communication network |

US7933814 | Sep 26, 2003 | Apr 26, 2011 | Hewlett-Packard Development Company, L.P. | Method and system to determine if a composite service level agreement (SLA) can be met |

US7948897 * | Aug 15, 2007 | May 24, 2011 | Adc Telecommunications, Inc. | Delay management for distributed communications networks |

US7965648 * | Jan 13, 2005 | Jun 21, 2011 | Nec Corporation | Speed calculation system |

US8023421 | Nov 20, 2006 | Sep 20, 2011 | Avaya Inc. | Method and apparatus for the assessment and optimization of network traffic |

US8037163 * | Oct 11, 2011 | Avaya Inc. | Alternative methodology in assessing network availability | |

US8046694 | Oct 25, 2011 | Gogrid, LLC | Multi-server control panel | |

US8090841 | Jan 3, 2012 | International Business Machines Corporation | Method of doing business over a network by transmission and retransmission of digital information on a network during time slots | |

US8095662 | Aug 4, 2008 | Jan 10, 2012 | Paul Lappas | Automated scheduling of virtual machines across hosting servers |

US8098648 * | Jan 7, 2005 | Jan 17, 2012 | Nec Corporation | Load distributing method |

US8280790 | Oct 2, 2012 | Gogrid, LLC | System and method for billing for hosted services | |

US8345570 * | Dec 10, 2009 | Jan 1, 2013 | Alcatel Lucent | Network impairment metrics for timing over packet |

US8374929 | Aug 7, 2007 | Feb 12, 2013 | Gogrid, LLC | System and method for billing for hosted services |

US8478283 | Sep 29, 2005 | Jul 2, 2013 | Apple Inc. | Method and system for capacity and coverage enhancement in wireless networks with relays |

US8503299 * | May 12, 2006 | Aug 6, 2013 | Apple, Inc. | Method and system for packet scheduling |

US8509215 * | Feb 2, 2011 | Aug 13, 2013 | Adc Telecommunications, Inc. | Delay management for distributed communications networks |

US8547855 * | Mar 21, 2006 | Oct 1, 2013 | Cisco Technology, Inc. | Method and apparatus to schedule multiple probes for active or passive monitoring of networks |

US8547864 * | Oct 22, 2010 | Oct 1, 2013 | Futurewei Technologies, Inc. | Layer one path delay compensation |

US8743718 | Jun 21, 2011 | Jun 3, 2014 | Adc Telecommunications, Inc. | End-to-end delay management for distributed communications networks |

US8751627 * | May 5, 2009 | Jun 10, 2014 | Accenture Global Services Limited | Method and system for application migration in a cloud |

US9264330 | Oct 13, 2013 | Feb 16, 2016 | Nicira, Inc. | Tracing host-originated logical network packets |

US9282019 | Jul 26, 2013 | Mar 8, 2016 | Nicira, Inc. | Tracing logical network packets through physical network |

US9344349 | Aug 15, 2013 | May 17, 2016 | Nicira, Inc. | Tracing network packets by a cluster of network controllers |

US9379956 | Jun 30, 2014 | Jun 28, 2016 | Nicira, Inc. | Identifying a network topology between two endpoints |

US9397920 | Jul 25, 2014 | Jul 19, 2016 | Nicira, Inc. | Multi-path network bandwidth estimation |

US9407580 | Jan 28, 2014 | Aug 2, 2016 | Nicira, Inc. | Maintaining data stored with a packet |

US9419874 | Mar 27, 2014 | Aug 16, 2016 | Nicira, Inc. | Packet tracing in a software-defined networking environment |

US9419889 | Mar 7, 2014 | Aug 16, 2016 | Nicira, Inc. | Method and system for discovering a path of network traffic |

US9450689 | Oct 3, 2014 | Sep 20, 2016 | Commscope Technologies Llc | Systems and methods for delay management in distributed antenna system with direct digital interface to base station |

US20030031185 * | Dec 26, 2001 | Feb 13, 2003 | Fujitsu Limited | Communication capability measuring equipment |

US20030053419 * | Aug 21, 2002 | Mar 20, 2003 | Toshiyuki Kanazawa | Packet communication quality measurement method and system |

US20030161321 * | Oct 17, 2001 | Aug 28, 2003 | Karam Mansour J. | Method and apparatus for characterizing the quality of a network path |

US20040105392 * | Nov 29, 2002 | Jun 3, 2004 | Saravut Charcranoon | Decentralized SLS monitoring in a differentiated service environment |

US20040174815 * | Mar 3, 2003 | Sep 9, 2004 | Ashish Khisti | Controlling admisson of data streams onto a network based on end-to-end measurements |

US20050054300 * | Oct 15, 2004 | Mar 10, 2005 | Andreas Vogel | Wireless network monitoring |

US20050080893 * | Sep 26, 2003 | Apr 14, 2005 | Castellanos Maria G. | Method and system to determine if a composite service level agreement (SLA) can be met |

US20050122987 * | Dec 9, 2003 | Jun 9, 2005 | Michael Ignatowski | Apparatus and method for modeling queueing systems with highly variable traffic arrival rates |

US20050243729 * | Apr 15, 2005 | Nov 3, 2005 | Apparent Networks, Inc. | Method and apparatus for automating and scaling active probing-based IP network performance monitoring and diagnosis |

US20060002306 * | Jun 30, 2005 | Jan 5, 2006 | Ronald Brown | Failure detection of path information corresponding to a transmission path |

US20060161647 * | Dec 22, 2004 | Jul 20, 2006 | Waldemar Wojtkiewicz | Method and apparatus providing measurement of packet latency in a processor |

US20060182039 * | Feb 15, 2005 | Aug 17, 2006 | Microsoft Corporation | High-accuracy packet pair for network bottleneck bandwidth measurement |

US20060215574 * | Mar 24, 2005 | Sep 28, 2006 | Microsoft Corporation | Bandwidth estimation in broadband access networks |

US20070002748 * | Jan 7, 2005 | Jan 4, 2007 | Tsuneo Nakata | Load distributing method |

US20070019552 * | May 12, 2006 | Jan 25, 2007 | Nortel Networks Limited | Method and system for packet scheduling |

US20070053373 * | Sep 2, 2005 | Mar 8, 2007 | Fitzgerald Cary W | Packetizing media for a time slotted communication system |

US20070115849 * | Nov 23, 2005 | May 24, 2007 | Svante Ekelin | Using filtering and active probing to evaluate a data transfer path |

US20070177521 * | Aug 2, 2006 | Aug 2, 2007 | Fujitsu Limited | Method for detecting communication condition, communication condition detecting system, and communication condition detecting apparatus |

US20080145047 * | Feb 2, 2005 | Jun 19, 2008 | Miguel De Vega Rodrigo | Method of Determining Delay in an Adaptive Path Optical Network |

US20080151923 * | Feb 22, 2008 | Jun 26, 2008 | International Business Machines Corporation | Apparatus for modeling queueing systems with highly variable traffic arrival rates |

US20080260000 * | Sep 29, 2005 | Oct 23, 2008 | Shalini Periyalwar | Method and System for Capacity and Coverage Enhancement in Wireless Networks With Relays |

US20080317026 * | Jul 10, 2008 | Dec 25, 2008 | International Business Machines Corporation | Method of Doing Business Over a Network by Transmission and Retransmission of Digital Information on a Network During Time Slots |

US20090046586 * | Aug 15, 2007 | Feb 19, 2009 | Adc Telecommunications, Inc. | Delay management for distributed communications networks |

US20090182605 * | Jul 16, 2009 | Paul Lappas | System and Method for Billing for Hosted Services | |

US20090190493 * | Jan 13, 2005 | Jul 30, 2009 | Tsuneo Nakata | Speed calculation system |

US20100284274 * | May 8, 2009 | Nov 11, 2010 | Bae Systems | System and method for determining a transmission order for packets at a node in a wireless communication network |

US20100287263 * | May 5, 2009 | Nov 11, 2010 | Huan Liu | Method and system for application migration in a cloud |

US20110122772 * | May 26, 2011 | Adc Telecommunications, Inc. | Delay management for distributed communications networks | |

US20110142079 * | Jun 16, 2011 | Alcatel-Lucent Canada Inc. | Network impairment metrics for timing over packet | |

US20110158105 * | Dec 27, 2009 | Jun 30, 2011 | Nicholas Duffield | Method and apparatus for detecting and localizing an anomaly for a network |

US20120099854 * | Oct 22, 2010 | Apr 26, 2012 | Futurewei Technologies, Inc. | Layer One Path Delay Compensation |

US20140122742 * | Nov 19, 2012 | May 1, 2014 | New Jersey Institute Of Technology | Measurement of clock skew between two remote hosts connected through computer networks |

CN102804690A * | Sep 23, 2011 | Nov 28, 2012 | 华为技术有限公司 | Layer one path delay compensation |

EP1424809A2 * | Nov 12, 2003 | Jun 2, 2004 | Alcatel | Decentralized SLS monitoring in a differentiated service environment |

EP1455490A2 * | Mar 3, 2004 | Sep 8, 2004 | Microsoft Corporation | Controlling admission of data streams onto a network based on end-to-end measurements |

Classifications

U.S. Classification | 370/252, 709/224, 709/233, 370/410, 370/236, 370/231 |

International Classification | H04L1/24, H04L12/56, H04L12/26, H04L12/24 |

Cooperative Classification | H04L43/0852, H04L41/142, H04L12/2697, H04L43/50, H04L41/5038, H04L47/115, H04L41/5003, H04L41/5064, H04L1/242, H04L47/283, H04L47/10 |

European Classification | H04L47/10, H04L47/11A, H04L43/50, H04L47/28A, H04L41/14A, H04L41/50F, H04L1/24C, H04L12/26T |

Legal Events

Date | Code | Event | Description |
---|---|---|---|

Feb 29, 2000 | AS | Assignment | Owner name: GTE LABORATORIES INCORPORATED, MASSACHUSETTS Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:SMITH, DONALD E.;LI, MAN;REEL/FRAME:010652/0756 Effective date: 20000228 |

Aug 31, 2000 | AS | Assignment | Owner name: VERIZON LABORATORIES INC., A DELAWARE CORPORATION, Free format text: CHANGE OF NAME;ASSIGNOR:GTE LABORATORIES INCORPORATED;REEL/FRAME:010921/0448 Effective date: 20000630 |

Feb 3, 2006 | FPAY | Fee payment | Year of fee payment: 4 |

Feb 8, 2010 | FPAY | Fee payment | Year of fee payment: 8 |

Feb 15, 2011 | AS | Assignment | Owner name: MERTEC CORP, CALIFORNIA Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:YOUNGER, GILBERT W.;REEL/FRAME:025785/0373 Effective date: 20110210 |

Jan 8, 2014 | FPAY | Fee payment | Year of fee payment: 12 |

Rotate